Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 186 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1048995 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1013. Min Act: -0.0001

Data Index: 30914 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0948. Min Act: -0.0001

Data Index: 810204 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0940. Min Act: -0.0001

Data Index: 812750 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1285984 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0925. Min Act: -0.0001

Data Index: 461605 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0882. Min Act: -0.0001

Data Index: 120325 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0919. Min Act: -0.0001

Data Index: 210531 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0860. Min Act: -0.0001

Data Index: 715200 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0856. Min Act: -0.0001

Data Index: 169573 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0887. Min Act: -0.0001

Data Index: 374916 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0857. Min Act: -0.0001

Data Index: 981802 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1128057 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0848. Min Act: -0.0001

Data Index: 838357 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0833. Min Act: -0.0001

Data Index: 317010 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1223973 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0866. Min Act: -0.0001

Data Index: 656207 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0803. Min Act: -0.0001

Data Index: 791885 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0827. Min Act: -0.0001

Data Index: 556602 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0819. Min Act: -0.0001

Data Index: 306115 (C4 (Web Text))

Max Activating Token Index: 541